Frequently Asked Questions

Agnes Video Generator is a completely free, open-source AI video tool. It uses Agnes AI's free models to turn text descriptions into narrated, subtitled multi-scene AI videos. No subscription, no credit card, no high-end GPU, and no usage limits.

Yes, completely free. Text, image, video, and voice generation are all powered by Agnes AI's free models. No payment, no high-end GPU, no watermarks, no token limits, and nothing hidden in the fine print.

Clone the GitHub repository (github.com/lcy362/agnes-video-generator), install the dependencies, set your Agnes AI API key, and launch the app. The whole setup takes about 2 minutes, and you can start making videos right after.

Agnes Video Generator is built for exactly this. It wraps Agnes AI's free video models in a ready-to-use web tool — no workflow setup, no coding, no API calls, no high-end GPU. Once installed, the whole creation flow is already wired up. Open your browser, type your idea, and get narrated, subtitled AI videos in one click. Simple enough for anyone.

Basic familiarity with running commands in a terminal is helpful for the initial setup. After that, the web interface is intuitive — just type your video idea in plain language and click generate. No coding or video editing experience is required.

It comes down to Agnes AI's vision. Founder Bruce Yang put it this way: 'The solution is not to suppress AI, but to make it a more equitable capability.' Agnes AI offers completely free model APIs for text, image, and video, and this project is built on top of them. All the heavy computation happens in the cloud, so you don't need a high-end GPU — anyone can make AI videos for nothing.

Open platform.agnes-ai.com, register with your email (free, no credit card required), then create and copy an API key from the console. You can paste it into the Web UI, set it as an environment variable, or use it directly in the official online demo. See the 'Get a Free API Key' guide for the full steps.

You can create four types of videos: Simple Video (a single clip from one text prompt), Creative Video (multi-scene story videos with AI-generated narration and subtitles), Manuscript Video (convert long articles or scripts into narrated video presentations), and Digital Anchor (AI-generated virtual anchor with TTS narration and subtitles, looped into a complete anchor video).

The interface supports 22 languages: Chinese, English, German, French, Dutch, Spanish, Portuguese, Italian, Russian, Japanese, Korean, Malay, Indonesian, Hindi, Turkish, Vietnamese, Bengali, Thai, Filipino, Arabic, Urdu, and Persian. Video narration supports multiple voice roles via Microsoft Edge TTS, including 4 Chinese voice characters.

Yes. You can control video resolution, duration, generation mode, seed values, negative prompts, character reference images, custom end frames, and video chaining modes (keyframes/ti2vid/none). Subtitle styling is also fully customizable.

Agnes Video Generator uses Microsoft Edge TTS (text-to-speech) for narration. It generates word-level timestamps for precise subtitle synchronization. The narration is automatically created based on your video's script or story content.

Multiple resolutions are supported, including standard and HD options. The exact resolutions depend on the underlying AI video model capabilities. You can select your preferred resolution before generating.

Agnes Video Generator runs on Linux, macOS, and Windows. It requires Node.js 18+ and a modern web browser. Since all AI processing happens via cloud APIs, you don't need a high-end GPU — your local machine's hardware specs are not a bottleneck.

Only the Agnes AI API key. Sign up at agnes-ai.com to get one for free. It covers text, image, video generation, and voice synthesis — all powered by Agnes AI's free models. No additional configuration needed.

Yes. The Manuscript Video mode is designed for batch processing — it takes a long text, splits it into segments, and generates videos for each segment sequentially with unified narration and subtitles.

Agnes Video Generator has a checkpoint resume feature. If a generation task is interrupted (network issue, system restart, etc.), it automatically resumes from the last successful checkpoint when restarted, so you don't lose progress. Most failures are caused by transient factors such as model service fluctuations, network timeouts, or rate limiting — click Retry Task in the failure panel first, and the task resumes from the failed step (checkpoint-based), usually recovering on its own.

Most failures are caused by transient factors such as model service fluctuations, network timeouts, or rate limiting. In the in-app failure panel, click Retry Task first — the task resumes from the failed step, and most cases recover on their own without resubmitting. If it still fails after several retries (≥ 2), the feedback area auto-expands, letting you copy the diagnostic info in one click and jump to a pre-filled GitHub Issue without describing your environment manually.

A 401 Unauthorized or "invalid token" response usually means the API Key does not match the domain it is being sent to — for example, a key issued on the global site being used against the China-domestic endpoint api.agnes-ai.cn (or the reverse). Keys issued for different sites are rejected when sent to the wrong domain. As of v6.4.2, each key can be bound to its own access domain, and a one-click Auto-detect domains button probes each key across com / cn / cn_bak and fills in the matching domain automatically. In the API Key panel, pick the domain that matches your key, or just run auto-detect. Global-site keys should use apihub.agnes-ai.com, or the cn_bak fallback domain (apihub.agnes-ai.cn, which accepts both domestic and global keys).

Feedback is available both in-app and on GitHub. When a task fails in the app, the failure panel offers Copy Diagnostic Info and Open a GitHub Issue buttons, automatically attaching the app version, task type, failed step, error message, and retry count to help maintainers pinpoint the problem. You can also visit the GitHub Issues page (github.com/lcy362/agnes-video-generator/issues) to check existing reports or open a new one.

Agnes Video Generator is self-hosted and open-source. Your prompts, generated content, and API keys stay on your local machine. No data is sent to any third-party servers beyond the AI API endpoints you configure.

Absolutely. The project is built for self-hosting: manual start.sh, Docker, npm CLI, or AI Agent — pick any of the four methods. The service runs at http://localhost:8765 with no external dependencies and no vendor lock-in. See the Self-Hosting Guide for complete commands.

Yes. Every release publishes images to GHCR and Docker Hub (linux/amd64 and linux/arm64) — pull latest and run, no Python or ffmpeg installation needed. Mounting the data directories is recommended so your videos and settings survive container recreation.

Yes. npx free-short-video starts the entire service with one command (or install globally and use free-short-video / fsv). It supports --port, --host 0.0.0.0 (LAN access) and --no-open; ffmpeg is bundled.

Unlike Runway, Pika, and Sora, Agnes Video Generator is completely free and open-source, with no high-end GPU required — all computation happens in the cloud. While paid tools may offer higher resolution or longer clips, Agnes provides the full pipeline — story generation, multi-scene video, narration, subtitles, and final output — at zero cost.

Most free AI video tools only generate short clips from single prompts. Agnes Video Generator provides a complete production pipeline with five creation modes, AI narration, automatic subtitles, and multi-scene storytelling — features typically found only in paid professional tools.

The software itself is open-source under the MIT license. Whether you can use the generated videos commercially depends on the terms of the underlying AI model APIs you configure. Check the terms of service for each API provider.